volume | PIER Journals

Abstract

Aircraft target detection in synthetic aperture radar (SAR) images faces numerous challenges, primarily including weak contrast, diverse morphologies, and faint signals, which are even more pronounced in complex backgrounds. Meanwhile, practical deployment environments are constrained by limited computational resources and energy consumption, making it essential to balance detection accuracy with model lightweight design. To address this, this paper proposes a lightweight detection network that integrates multi-branch feature enhancement. First, a Parallel Aggregation and Calibration (PAC) module is designed to achieve collaborative modeling of local and global information through multi-scale dilated convolutions; second, a Moment Channel Attention (MCA) module based on higher-order statistical features is introduced to enhance the model's sensitivity to weak signals and target boundaries; finally, during the network fusion stage, the branch calibration connections in the PAC module are removed, and a frequency-domain-driven Efficient Discriminative Frequency domain-based FFN (EDFFN) module is incorporated to improve detailed representation of low-contrast and blurred targets. Experimental results on the SAR-Aircraft-1.0 dataset demonstrate that the proposed method achieves 93.94% mAP, while reducing model parameters by 56% and computational complexity by 36% compared to YOLOv12s, effectively balancing performance and lightweight requirements.

1. Zhang, Qingjun, Huangjiang Fan, Yuxiao Qin, and Yashi Zhou, "Advances in interferometric synthetic aperture radar technology and systems and recent advances in Chinese SAR missions," Sensors, Vol. 25, No. 15, 4616, 2025.
doi:10.3390/s25154616 Google Scholar

2. Yoon, Seokchan, Moonseok Kim, Mooseok Jang, Youngwoon Choi, Wonjun Choi, Sungsam Kang, and Wonshik Choi, "Deep optical imaging within complex scattering media," Nature Reviews Physics, Vol. 2, No. 3, 141-158, 2020.
doi:10.1038/s42254-019-0143-2 Google Scholar

3. Liu, Tao, Ziyuan Yang, Yanni Jiang, and Gui Gao, "Review of ship detection in polarimetric synthetic aperture imagery," Journal of Radars, Vol. 10, No. 1, 1-19, 2021.
doi:10.12000/JR20155 Google Scholar

4. Hu, Cheng, Zhiyang Chen, Yuanhao Li, Xichao Dong, and Stephen Hobbs, "Research progress on geosynchronous synthetic aperture radar," Fundamental Research, Vol. 1, No. 3, 346-363, 2021.
doi:10.1016/j.fmre.2021.04.008 Google Scholar

5. Kıvanç, Ercan, Gülfem Tuzkaya, and Özalp Vayvay, "Safety management system and risk-based approach in aviation maintenance: A systematic literature review," Safety Science, Vol. 184, 106755, 2025.
doi:10.1016/j.ssci.2024.106755 Google Scholar

6. Ahmed, Shams Forruque, Md. Sakib Bin Alam, Maruf Hassan, Mahtabin Rodela Rozbu, Taoseef Ishtiak, Nazifa Rafa, M. Mofijur, A. B. M. Shawkat Ali, and Amir H. Gandomi, "Deep learning modelling techniques: Current progress, applications, advantages, and challenges," Artificial Intelligence Review, Vol. 56, No. 11, 13521-13617, 2023.
doi:10.1007/s10462-023-10466-8 Google Scholar

7. Singh, Prabhishek and Raj Shree, "Analysis and effects of speckle noise in SAR images," 2016 2nd International Conference on Advances in Computing, Communication, & Automation (ICACCA) (Fall), 1-5, Bareilly, India, 2016.
doi:10.1109/icaccaf.2016.7748978

8. Khan, Asifullah, Anabia Sohail, Umme Zahoora, and Aqsa Saeed Qureshi, "A survey of the recent architectures of deep convolutional neural networks," Artificial Intelligence Review, Vol. 53, No. 8, 5455-5516, 2020.
doi:10.1007/s10462-020-09825-6 Google Scholar

9. Xiao, Xiayang, Hecheng Jia, Penghao Xiao, and Haipeng Wang, "Aircraft detection in SAR images based on peak feature fusion and adaptive deformable network," Remote Sensing, Vol. 14, No. 23, 6077, 2022.
doi:10.3390/rs14236077 Google Scholar

10. Kang, Yuzhuo, Zhirui Wang, Haoyu Zuo, Yidan Zhang, Zhujun Yang, Xian Sun, and Kun Fu, "ST-Net: Scattering topology network for aircraft classification in high-resolution SAR images," IEEE Transactions on Geoscience and Remote Sensing, Vol. 61, 1-17, 2023.
doi:10.1109/tgrs.2023.3236987 Google Scholar

11. Zhao, Chenxi, Siqian Zhang, Ru Luo, Sijia Feng, and Gangyao Kuang, "Scattering features spatial-structural association network for aircraft recognition in SAR images," IEEE Geoscience and Remote Sensing Letters, Vol. 20, 1-5, 2023.
doi:10.1109/lgrs.2023.3280442 Google Scholar

12. Zhou, Jie, Chao Xiao, Bo Peng, Zhen Liu, Li Liu, Yongxiang Liu, and Xiang Li, "DiffDet4SAR: Diffusion-based aircraft target detection network for SAR images," IEEE Geoscience and Remote Sensing Letters, Vol. 21, 1-5, 2024.
doi:10.1109/lgrs.2024.3386020 Google Scholar

13. Islam, Md. Tauhidul and Lei Xing, "Deciphering the feature representation of deep neural networks for high-performance AI," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 46, No. 8, 5273-5287, 2024.
doi:10.1109/tpami.2024.3363642 Google Scholar

14. Rodriguez-Conde, Ivan, Celso Campos, and Florentino Fdez-Riverola, "Optimized convolutional neural network architectures for efficient on-device vision-based object detection," Neural Computing and Applications, Vol. 34, No. 13, 10469-10501, 2022.
doi:10.1007/s00521-021-06830-w Google Scholar

15. Zhang, Songming, Yuxiao Luo, Ziyu Lyu, and Xiaofeng Chen, "ShiftKD: Benchmarking knowledge distillation under distribution shift," Neural Networks, Vol. 192, 107838, 2025.
doi:10.1016/j.neunet.2025.107838 Google Scholar

16. Wu, Hailang, Hanbo Sang, Zenghui Zhang, and Weiwei Guo, "LRMSNet: A new lightweight detection algorithm for multi-scale SAR objects," Remote Sensing, Vol. 16, No. 12, 2082, Jun. 2024.
doi:10.3390/rs16122082 Google Scholar

17. Luo, Ru, Lifu Chen, Jin Xing, Zhihui Yuan, Siyu Tan, Xingmin Cai, and Jielan Wang, "A fast aircraft detection method for SAR images based on efficient bidirectional path aggregated attention network," Remote Sensing, Vol. 13, No. 15, 2940, 2021.
doi:10.3390/rs13152940 Google Scholar

18. Luo, Ru, Qishan He, Lingjun Zhao, Siqian Zhang, Gangyao Kuang, and Kefeng Ji, "Geospatial contextual prior-enabled knowledge reasoning framework for fine-grained aircraft detection in panoramic SAR imagery," IEEE Transactions on Geoscience and Remote Sensing, Vol. 62, 2024.
doi:10.1109/tgrs.2024.3487780 Google Scholar

19. Zhu, Wenbo, Liu Zhang, Chunqiang Lu, Guowei Fan, Ying Song, Jianbo Sun, and Xueying Lv, "FEMSFNet: Feature enhancement and multi-scales fusion network for SAR aircraft detection," Remote Sensing, Vol. 16, No. 9, 1589, 2024.
doi:10.3390/rs16091589 Google Scholar

20. Yang, C., G. Q. Gong, C. Liu, J. W. Deng, and Y. X. Ye, "RMSOConvNeXt: A lightweight CNN network for robust SAR and optical image matching under strong noise interference," IEEE Transactions on Geoscience and Remote Sensing, Vol. 63, 2025.
doi:10.1109/tgrs.2025.3550936 Google Scholar

21. Jiang, Yangbo, Zhiwei Jiang, Le Han, Zenan Huang, and Nenggan Zheng, "MCA: Moment channel attention networks," Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, No. 3, 2579-2588, Vancouver, Canada, Feb. 2024.
doi:10.1609/aaai.v38i3.28035

22. Kong, Lingshun, Jiangxin Dong, Jinhui Tang, Ming-Hsuan Yang, and Jinshan Pan, "Efficient visual state space model for image deblurring," 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 12710-12719, Nashville, TN, USA, 2025.
doi:10.1109/cvpr52734.2025.01186

23. Fernandez, Alfredo and Ankur Mali, "TeLU activation function for fast and stable deep learning," arXiv:2412.20269, 2024. Google Scholar

24. Wang, Zhirui, Yuzhuo Kang, Xuan Zeng, Yuelei Wang, Ting Zhang, and Xian Sun, "SAR-AIRcraft-1.0: High-resolution SAR aircraft detection and recognition dataset," Journal of Radars, Vol. 12, No. 4, 906-922, 2023.
doi:10.12000/JR23043 Google Scholar

Mr. Zengyuan Guo

Professor Wei Xu

Professor Pingping Huang

Prof. Weixian Tan

Dr. Zhiqi Gao